Information-Retrieval

About Dense embedding-based retrieval is widely used for semantic search and ranking. However, conventional two-stage approaches, involving contrastive embedding learning followed by approximate nearest neighbor search (ANNS), can suffer from misalignment between these stages. This mismatch degrades retrieval performance. We propose End-to-end Hierarchical Indexing (EHI), a novel method that directly addresses this issue by jointly optimizing embedding generation and ANNS structure. EHI leverages a dual encoder for embedding queries and documents while simultaneously learning an inverted file index (IVF)-style tree structure....

A parameter efficient encoder only model for multi-shot retrieval (aka extreme classification)

A light-weight mini-batch creation technique that offers provably accurate in-batch negative samples for training retrieval models. This allows training with larger mini-batches offering significantly faster convergence and higher accuracies than existing negative sampling techniques.

Learnable graph-based search index for classification/retrieval in large output space, scalable to label space on a single A100 GPU, achieves SOTA on multiple large-scale extreme classification benchmarks

This paper proposes Generalized Zero-shot XML (GZXML), a paradigm where the task is to tag a data point with the most relevant labels from a large universe of both seen and unseen labels.

This paper introduces a new learning paradigm called eXtreme Regression (XR) whose objective is to accurately predict the numerical degrees of relevance of an extremely large number of labels to a data point. XR can provide elegant solutions to many large-scale ranking and recommendation applications including Dynamic Search Advertising (DSA).